mlsanityData to 7 Oct 2026

A two-stage data association approach for 3D Multi-object Tracking

arXiv 2101.08684 ↗First posted 21 Jan 2021cs.CV cs.AI cs.ROcited by 3

Not on the map. Why?

Abstract (arXiv)

Multi-object tracking (MOT) is an integral part of any autonomous driving pipelines because itproduces trajectories which has been taken by other moving objects in the scene and helps predicttheir future motion. Thanks to the recent advances in 3D object detection enabled by deep learning,track-by-detection has become the dominant paradigm in 3D MOT. In this paradigm, a MOT systemis essentially made of an object detector and a data association algorithm which establishes track-to-detection correspondence. While 3D object detection has been actively researched, associationalgorithms for 3D MOT seem to settle at a bipartie matching formulated as a linear assignmentproblem (LAP) and solved by the Hungarian algorithm. In this paper, we adapt a two-stage dataassociation method which was successful in image-based tracking to the 3D setting, thus providingan alternative for data association for 3D MOT. Our method outperforms the baseline using one-stagebipartie matching for data association by achieving 0.587 AMOTA in NuScenes validation set.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 21 Jan 2021.

Builds on

24 of 36 references.

References · 24

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  6. 2019Objects as Pointscited by 1,172
  7. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  8. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  9. 2016Simple Online and Realtime Trackingcited by 862
  10. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  11. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  12. 2020PnPNet: End-to-End Perception and Prediction with Tracking in the Loopcited by 143
12 more
  1. 2015MOTChallenge 2015: Towards a Benchmark for Multi-Target Trackingcited by 133
  2. 2019IoU Loss for 2D/3D Object Detectioncited by 128
  3. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  4. 2016Learning by tracking: Siamese CNN for robust target associationcited by 79
  5. 2020Probabilistic 3D Multi-Object Tracking for Autonomous Drivingcited by 64
  6. 2020AFDet: Anchor Free One Stage 3D Object Detectioncited by 63
  7. 2020AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metricscited by 63
  8. 2020Improving 3D Object Detection through Progressive Population Based Augmentationcited by 41
  9. 2018Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filteringcited by 32
  10. 2017Poisson multi-Bernoulli mixture filter: direct derivation and implementationcited by 29
  11. 2017Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Trackingcited by 18
  12. 20201st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptationcited by 15

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2023You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Trackingcited by 8
  2. 20233D Multiple Object Tracking on Autonomous Driving: A Literature Reviewcited by 4
  3. 2022Online panoptic 3D reconstruction as a Linear Assignment Problemcited by 0